Generating query answers from a user's history

• US 10,515,076 B1
• Filed: 01/31/2017
• Issued: 12/24/2019
• Est. Priority Date: 04/12/2013
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google LLC (Alphabet Inc.)
• Inventors: Wiegand, Nathan, Horling, Bryan C., Smart, Jason L.
• Primary Examiner(s): Dang, Thanh-Ha
• Application Number:
  US15/421,005
• Time in Patent Office: 1,057 Days
• Field of Search: 707769
• CPC Class Codes: G06F 16/243 Natural language query formulation
• CPC Class Codes: G06F 16/24539 using cached or materialised query results
• CPC Class Codes: G06F 16/955 using information identifiers, e.g. uniform resource locators [URL]

Abstract

One or more servers receive a natural language query from a client device associated with a user. The one or more servers classify the natural language query as a query that seeks information previously accessed by the user. The one or more servers then obtain a response to the natural language query from one or more collections of documents, wherein each document in the one or more collections of documents was previously accessed by the user. The one or more servers generate search results based on the response. Then, the one or more servers communicate the search results to the client device.

Claims

1. A computer-implemented method for identifying and providing information in response to a natural language user query requesting content, the method comprising:

receiving, by voice input from a user, the natural language user query, wherein the natural language user query includes terms that indicate a particular topic, and terms that indicate that the user viewed, prior to providing the voice input, a resource that includes content of the particular topic;

determining, from the terms of the natural language user query, that the natural language user query seeks information previously accessed by the user based on the terms that indicate that the user accessed, prior to providing the voice input, the resource that includes the content of the particular topic;

determining, by one or more processors, a resource set comprising one or more resources that satisfy the content requested by the natural language user query;

determining, by the one or more processors and based on determining that the natural language query seeks information previously accessed by the user, a resource subset of the resource set, the resource subset comprising one or more resources that the user has previously accessed prior to providing the voice input; and

providing, for output as a result, information from the one or more resources that the user has previously accessed in response to the natural language user query.

2. The computer-implemented method of claim 1, wherein determining that the natural language user query seeks information previously accessed by the user comprises:

determining that the natural language user query seeks a resource previously accessed by the user in a previous search session between the user and a search engine.

3. The computer-implemented method of claim 1, further comprising:

determining, from the terms of the natural language user query, that the natural language user query seeks one or more resources that satisfy one or more of a time criterion specifying at least a time prior to the user providing the voice input, a topical criterion, and a device criterion; and

determining a second resource subset comprising one or more resources from the resource subset that satisfy the one or more of the time criterion, the topical criterion, and the device criterion,

wherein providing, for output as the result, the information from the one or more resources that the user has previously accessed comprises providing information from the one or more resources of the second resource subset.

4. The computer-implemented method of claim 3, wherein:

the one or more of the time criterion, the topical criterion, and the device criterion are determined, in part, from the terms of the natural language user query received by the voice input from the user;

the time criterion includes a criterion specifying a particular period of time;

the topical criterion includes a criterion specifying one or more topics included in the information previously accessed by the user; and

the device criterion includes a criterion specifying one or more devices used to by the user to obtain the information previously accessed by the user.

5. The computer-implemented method of claim 1, wherein determining, from the terms of the natural language user query, that the natural language user query seeks information previously accessed by the user comprises:

modifying the query by replacing one or more terms of the natural language query with one or more synonyms of the respective one or more terms of the natural language query before providing, for output as the result, the information from the one or more resources that the user has previously accessed.

6. The computer-implemented method of claim 1, wherein determining that the natural language user query seeks information previously accessed by the user comprises:

comparing one or more of the terms of the natural language query to one or more terms identified as corresponding to queries seeking previously accessed information; and

determining that the natural language user query seeks information previously accessed by the user based on the comparing of the one or more of the terms of the natural language query to the one or more terms identified as corresponding to queries seeking previously accessed information.

7. The computer-implemented method of claim 6, wherein determining that the natural language user query seeks information previously accessed by the user further comprises:

based on the comparing of the one or more of the terms of the natural language query to the one or more terms identified as corresponding to queries seeking previously accessed information, determining a level of similarity between the one or more of the terms of the natural language query and the one or more terms identified as corresponding to queries seeking previously accessed information;

determining whether the level of similarity satisfies a similarity threshold; and

providing an indication that the natural language query is a type of query that seeks information previously accessed by the user in response to the level of similarity satisfying the similarity threshold.

8. One or more non-transitory computer-readable storage media comprising instructions, which, when executed by one or more computing devices, cause the one or more computing devices to perform operations comprising:

receiving, by voice input from a user, the natural language user query, wherein the natural language user query includes terms that indicate a particular topic, and terms that indicate that the user viewed, prior to providing the voice input, a resource that includes content of the particular topic;

determining, from the terms of the natural language user query, that the natural language user query seeks information previously accessed by the user based on the terms that indicate that the user accessed, prior to providing the voice input, the resource that includes the content of the particular topic;

determining a resource set comprising one or more resources that satisfy the content requested by the natural language user query;

determining, based on determining that the natural language query seeks information previously accessed by the user, a resource subset of the resource set, the resource subset comprising one or more resources that the user has previously accessed prior to providing the voice input; and

providing, for output as a result, information from the one or more resources that the user has previously accessed in response to the natural language user query.

9. The one or more non-transitory computer-readable storage media of claim 8, wherein determining that the natural language user query seeks information previously accessed by the user comprises:

determining that the natural language user query seeks a resource previously accessed by the user in a previous search session between the user and a search engine.

10. The one or more non-transitory computer-readable storage media of claim 8, wherein the operations further comprise:

determining, from the terms of the natural language user query, that the natural language user query seeks one or more resources that satisfy one or more of a time criterion specifying at least a time prior to the user providing the voice input, a topical criterion, and a device criterion; and

determining a second resource subset comprising one or more resources from the resource subset that satisfy the one or more of the time criterion, the topical criterion, and the device criterion, and

wherein providing, for output as the result, the information from the one or more resources that the user has previously accessed comprises providing information from the one or more resources of the second resource subset.

11. The one or more non-transitory computer-readable storage media of claim 10, wherein:

the one or more of the time criterion, the topical criterion, and the device criterion are determined, in part, from the terms of the natural language user query received by the voice input from the user;

the time criterion includes a criterion specifying a particular period of time;

the topical criterion includes a criterion specifying one or more topics included in the information previously accessed by the user; and

the device criterion includes a criterion specifying one or more devices used to by the user to obtain the information previously accessed by the user.

12. The one or more non-transitory computer-readable storage media of claim 8, wherein determining, from the terms of the natural language user query, that the natural language user query seeks information previously accessed by the user comprises:

modifying the query by replacing one or more terms of the natural language query with one or more synonyms of the respective one or more terms of the natural language query before providing, for output as the result, the information from the one or more resources that the user has previously accessed.

13. The one or more non-transitory computer-readable storage media of claim 8, wherein determining that the natural language user query seeks information previously accessed by the user comprises:

comparing one or more of the terms of the natural language query to one or more terms identified as corresponding to queries seeking previously accessed information;

based on the comparing of the one or more of the terms of the natural language query to the one or more terms identified as corresponding to queries seeking previously accessed information, determining a level of similarity between the one or more of the terms of the natural language query and the one or more terms identified as corresponding to queries seeking previously accessed information;

determining whether the level of similarity satisfies a similarity threshold; and

providing an indication that the natural language query is a type of query that seeks information previously accessed by the user in response to the level of similarity satisfying the similarity threshold; and

determining that the natural language user query seeks information previously accessed by the user in response to the level of similarity satisfying the similarity threshold.

14. A system comprising:

one or more computing devices and one or more storage devices storing instructions, which when executed by the one or more computing devices, cause the one or more computing devices to perform operations comprising;

receiving, by voice input from a user, the natural language user query, wherein the natural language user query includes terms that indicate a particular topic, and terms that indicate that the user viewed, prior to providing the voice input, a resource that includes content of the particular topic;

determining, from the terms of the natural language user query, that the natural language user query seeks information previously accessed by the user based on the terms that indicate that the user accessed, prior to providing the voice input, the resource that includes the content of the particular topic;

determining, by one or more processors, a resource set comprising one or more resources that satisfy the content requested by the natural language user query;

determining, by the one or more processors and based on determining that the natural language query seeks information previously accessed by the user, a resource subset of the resource set, the resource subset comprising one or more resources that the user has previously accessed prior to providing the voice input; and

providing, for output as a result, information from the one or more resources that the user has previously accessed in response to the natural language user query.

15. The system of claim 14, wherein determining that the natural language user query seeks information previously accessed by the user comprises:

determining that the natural language user query seeks a resource previously accessed by the user in a previous search session between the user and a search engine.

16. The system of claim 14, wherein the operations further comprise:

determining, from the terms of the natural language user query, that the natural language user query seeks one or more resources that satisfy one or more of a time criterion specifying at least a time prior to the user providing the voice input, a topical criterion, and a device criterion; and

determining a second resource subset comprising one or more resources from the resource subset that satisfy the one or more of the time criterion, the topical criterion, and the device criterion, and

wherein providing, for output as the result, the information from the one or more resources that the user has previously accessed comprises providing information from the one or more resources of the second resource subset.

17. The system of claim 16, wherein:

the one or more of the time criterion, the topical criterion, and the device criterion are determined, in part, from the terms of the natural language user query received by the voice input from the user;

the time criterion includes a criterion specifying a particular period of time;

the topical criterion includes a criterion specifying one or more topics included in the information previously accessed by the user; and

the device criterion includes a criterion specifying one or more devices used to by the user to obtain the information previously accessed by the user.

18. The system of claim 14, wherein determining, from the terms of the natural language user query, that the natural language user query seeks information previously accessed by the user comprises:

modifying the query by replacing one or more terms of the natural language query with one or more synonyms of the respective one or more terms of the natural language query before providing, for output as the result, the information from the one or more resources that the user has previously accessed.

19. The system of claim 14, wherein determining that the natural language user query seeks information previously accessed by the user comprises:

comparing one or more of the terms of the natural language query to one or more terms identified as corresponding to queries seeking previously accessed information;

based on the comparing of the one or more of the terms of the natural language query to the one or more terms identified as corresponding to queries seeking previously accessed information, determining a level of similarity between the one or more of the terms of the natural language query and the one or more terms identified as corresponding to queries seeking previously accessed information;

determining whether the level of similarity satisfies a similarity threshold; and

providing an indication that the natural language query is a type of query that seeks information previously accessed by the user in response to the level of similarity satisfying the similarity threshold; and

determining that the natural language user query seeks information previously accessed by the user in response to the level of similarity satisfying the similarity threshold.

20. A computer-implemented method comprising:

determining, based on content of a natural language search query spoken by a user and submitted to a search engine, wherein the natural language user query includes terms that indicate a topical criteria, terms that indicate a time criteria that specifies a time period that occurs prior to the user speaking the natural language search query, and terms that indicate that the user viewed, prior to speaking the natural language query, a resource that includes content of the particular topic, that the natural language search query is likely a query seeking information from one or more resources previously accessed by the user during a previous search session between the user and the search engine, the determination based on the terms that indicate that the user accessed, prior to speaking the natural language query, the resource that includes the content of the particular topic;

in response to determining that the natural language search query is likely a query seeking information from one or more resources previously accessed by the user during a previous search session between the user and the search engine, selecting, from among a collection of resources previously accessed by the user during a previous search session between the user and the search engine, a subset of one or more resources that satisfy the time criteria and the topical criteria specified by the natural language search query; and

providing for output, in response to the natural language search query, information from one or more resources of the subset of one or more resources that satisfy the time criteria and the topical criteria specified by the natural language search query.